Register D&D item event pipeline

internal/modules/dnd/validate/itemevents/source_relatedness/validator.go

@@ -0,0 +1,88 @@
+// Package sourcerelatedness warns when item-event evidence does not mention its item.
+package sourcerelatedness
+
+import (
+	"context"
+	"fmt"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
+	itemeventshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemevents/shape"
+)
+
+const (
+	Key               = "extract/dnd/item-events/source_relatedness"
+	WarningReasonCode = "item_event_source_unrelated"
+	OmittedReasonCode = "item_event_relatedness_warnings_omitted"
+	policy            = "dnd.item_events.source_relatedness.v1"
+)
+
+type Options struct{}
+type Validator struct{}
+
+var _ contracts.TypedValidator[dnd.ItemEventList] = (*Validator)(nil)
+var _ pipeline.CheckpointFingerprintProvider = (*Validator)(nil)
+
+func New(Options) *Validator      { return &Validator{} }
+func (v *Validator) Name() string { return Key }
+func (v *Validator) ExecutionClass() contracts.ExecutionClass {
+	return contracts.ExecutionClassDeterministic
+}
+func (v *Validator) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
+	return []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}
+}
+
+// Validate performs advisory source grounding only. Shape and range failures
+// are intentionally left to their blocking owners.
+func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.ItemEventList]) (contracts.ValidationResult, error) {
+	if itemeventshape.Validate(req.Value) != nil {
+		return contracts.ValidationResult{Approved: true}, nil
+	}
+	resolver, err := shared.NewCitationResolver(req.Source)
+	if err != nil {
+		return contracts.ValidationResult{Approved: true}, nil
+	}
+
+	warnings := make([]contracts.Warning, 0)
+	for index, event := range req.Value.Events {
+		citedText, err := resolver.CitedText(event.SourceRefs)
+		if err != nil || shared.ContainsTokenSequence(citedText, event.Name) {
+			continue
+		}
+		warnings = append(warnings, contracts.Warning{
+			Scope:      fmt.Sprintf("events[%d]", index),
+			ReasonCode: WarningReasonCode,
+			Message:    fmt.Sprintf("item event name %s was not found in cited source text", diagnostics.Quote(event.Name)),
+		})
+	}
+	return contracts.ValidationResult{
+		Approved: true,
+		Warnings: diagnostics.LimitWarnings(warnings, "item_events", OmittedReasonCode),
+	}, nil
+}
+
+func Spec() pipeline.ValidatorSpec {
+	return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
+}
+
+func Register(registry *pipeline.ValidatorRegistry) error {
+	return pipeline.RegisterTypedValidatorBuilder(registry, dnd.ItemEventListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.ItemEventList], error) {
+		options, err := DecodeOptions(request.Options)
+		if err != nil {
+			return nil, err
+		}
+		return New(options), nil
+	})
+}
+
+func DecodeOptions(options map[string]any) (Options, error) {
+	if err := pipeline.RejectUnknownOptions(options); err != nil {
+		return Options{}, err
+	}
+	return Options{}, nil
+}
+
+func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }

internal/modules/dnd/validate/itemevents/source_relatedness/validator_test.go

@@ -0,0 +1,74 @@
+package sourcerelatedness
+
+import (
+	"context"
+	"reflect"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
+)
+
+func TestValidatorMatchesTokenSequencesAcrossRanges(t *testing.T) {
+	doc := &source.SourceDocument{ID: "session", Units: []source.SourceUnit{
+		{ID: 1, Text: "Aria finds a potion,"},
+		{ID: 2, Text: "of healing in the chest."},
+		{ID: 3, Text: "The group rests."},
+	}}
+	value := dnd.ItemEventList{Events: []dnd.ItemEvent{
+		{Name: "POTION OF HEALING", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 1}, {SourceID: doc.ID, StartUnitID: 2, EndUnitID: 2}}},
+		{Name: "missing-item", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 3, EndUnitID: 3}}},
+	}}
+	references := contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{
+		"glossary": {Items: []contracts.ReferenceItem{{Content: []byte("missing-item")}}},
+	}}
+	result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Source: doc, References: references, Value: value})
+	if err != nil || !result.Approved || len(result.Warnings) != 1 {
+		t.Fatalf("Validate() = %#v, %v", result, err)
+	}
+	if warning := result.Warnings[0]; warning.Scope != "events[1]" || warning.ReasonCode != WarningReasonCode || !strings.Contains(warning.Message, "missing-item") {
+		t.Fatalf("warning = %#v", warning)
+	}
+}
+
+func TestValidatorDefersMalformedAndUnreadableEvidence(t *testing.T) {
+	doc := &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1, Text: "a potion"}}}
+	for _, value := range []dnd.ItemEventList{
+		{Events: []dnd.ItemEvent{{Name: "", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 1}}}}},
+		{Events: []dnd.ItemEvent{{Name: "potion", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 99, EndUnitID: 99}}}}},
+	} {
+		result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Source: doc, Value: value})
+		if err != nil || !result.Approved || len(result.Warnings) != 0 {
+			t.Fatalf("deferred result = %#v, %v", result, err)
+		}
+	}
+}
+
+func TestValidatorBoundsWarningsAndRegistersPolicy(t *testing.T) {
+	count := diagnostics.MaxWarnings + 5
+	events := make([]dnd.ItemEvent, count)
+	for index := range events {
+		events[index] = dnd.ItemEvent{Name: "missing item", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}
+	}
+	result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{
+		Source: &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1, Text: "nothing useful"}}},
+		Value:  dnd.ItemEventList{Events: events},
+	})
+	if err != nil || !result.Approved || len(result.Warnings) != diagnostics.MaxWarnings || result.Warnings[len(result.Warnings)-1].ReasonCode != OmittedReasonCode {
+		t.Fatalf("Validate() = %#v, %v", result, err)
+	}
+	if got := New(Options{}).CheckpointFingerprints(); !reflect.DeepEqual(got, []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}) {
+		t.Fatalf("CheckpointFingerprints() = %#v", got)
+	}
+	registry := pipeline.NewValidatorRegistry()
+	if err := Register(registry); err != nil {
+		t.Fatalf("Register() error = %v", err)
+	}
+	if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
+		t.Fatal("DecodeOptions() accepted unknown option")
+	}
+}